Overview

Create dt-method-07-deep.instructions.md — the on-demand deep instruction file for Method 7: High-Fidelity Prototypes. Loaded explicitly by the coach via read_file when advanced hi-fi prototyping expertise is needed. Method 7 is unique with 3 hats, and this deep file provides extended expertise for all three: advanced fidelity translation strategies, technology selection frameworks, and specification writing patterns.

Target File

.github/instructions/dt-method-07-deep.instructions.md

Frontmatter

---
description: 'Deep expertise for Method 7: High-Fidelity Prototypes — fidelity translation, architecture patterns, and specification writing'
applyTo: ''
---

Note: applyTo is empty — this file is loaded on-demand by the coach agent, not auto-loaded by glob.

Required Content

Advanced Fidelity Translation (Supports Hat 1: Fidelity Translator)

Moving from lo-fi to hi-fi requires deliberate decisions:

• Fidelity mapping matrix: For each lo-fi prototype element, decide: replicate exactly, reinterpret for hi-fi, or discard as lo-fi artifact
• Learning preservation: How to carry forward lo-fi insights without being constrained by lo-fi implementation choices
• Fidelity gradient: Not everything needs to reach the same fidelity — map which components need hi-fi (for testing) and which can remain rough
• Translation anti-patterns: Over-translating (importing all lo-fi roughness into hi-fi), under-translating (ignoring lo-fi learnings and starting fresh), and fidelity mismatch (hi-fi visuals with lo-fi functionality)

Technology Selection Frameworks (Supports Hat 2: Technical Architect)

Guiding technology choices for functional prototypes:

• Prototype-appropriate technology: Frameworks and tools optimized for speed over maintainability — the prototype will likely be rebuilt for production
• Build-vs-simulate decision tree: When to build real functionality vs. simulating it (Wizard of Oz at hi-fi level)
• Architecture trade-off analysis: Monolith vs. modular, local vs. cloud, real data vs. synthetic data — framed as prototype decisions, not production decisions
• Technical debt budget: Explicit acknowledgment that hi-fi prototypes accumulate debt — establish what's acceptable and what would block testing

Specification Writing Patterns (Supports Hat 3: Specification Writer)

Creating specifications that serve downstream stakeholders:

• Specification audience mapping: Different spec formats for developers, designers, stakeholders, and testers
• Decision rationale capture: Document why choices were made, not just what was chosen — essential for production reimplementation
• Assumption documentation: Technical assumptions baked into the prototype that may not hold at production scale
• Gap documentation: What the prototype intentionally doesn't cover and why

Manufacturing-Specific Hi-Fi Patterns

From DT4HVE manufacturing context:

• PLC/SCADA prototyping: Simulating industrial control system interactions at sufficient fidelity for operator testing
• Digital twin prototyping: Creating simplified digital representations of physical systems for testing
• Safety-critical prototype boundaries: Explicit constraints on what can be prototyped functionally vs. what must remain simulated for safety reasons
• Operator interface fidelity: Prototyping at the fidelity level operators need to give meaningful feedback (screen layout, alarm patterns, interaction timing)

Token Budget

Target: ~2,000-3,000 tokens (on-demand tier)

How to Build This File

This is an .instructions.md file — use the prompt-builder agent (not task-implementor) for the authoring phase. The prompt-builder includes built-in Prompt Quality Criteria validation and sandbox testing specific to AI artifacts (.instructions.md, .prompt.md, .agent.md, SKILL.md).

Workflow: /task-research → /task-plan → /prompt-build → /task-review
Between each phase, run /clear to reset context.

Phase 1: Research

Source Material:

1. design-thinking-for-hve-capabilities/guidance/07-high-fidelity-prototypes.md
2. .github/instructions/dt-method-07-hifi-prototypes.instructions.md (already-built method-tier file)

The DT4HVE guidance file lives in the DT4HVE repository. If you don't have local access, ask the user to provide it or use read_file if the repo is cloned nearby.

Steps:

1. Read both source materials above.
2. Read .github/instructions/prompt-builder.instructions.md for authoring standards.
3. Read any existing dt-method-*-deep instruction files for structural precedent.
4. Gather content on fidelity translation patterns, 3-hat deep expertise, technology selection approaches, and specification writing frameworks.

Starter prompt:

/task-research

Research for dt-method-07-deep.instructions.md (on-demand deep file)

Read the DT4HVE source material at design-thinking-for-hve-capabilities/guidance/07-high-fidelity-prototypes.md AND the already-built method-tier file at .github/instructions/dt-method-07-hifi-prototypes.instructions.md. Extract advanced/deep-dive content that goes BEYOND the basic method-tier coverage:
- Fidelity translation patterns — advanced mapping from lo-fi concepts to hi-fi implementations with anti-patterns
- 3-hat deep expertise — advanced techniques for each hat (Fidelity Translator, Technical Architect, Specification Writer)
- Technology selection approaches — frameworks for choosing the right tools and platforms per fidelity level
- Specification writing frameworks — structured approaches for converting prototypes to implementable specs
- Manufacturing-specific hi-fi patterns from DT4HVE's domain expertise

Also read .github/instructions/prompt-builder.instructions.md for authoring standards and any existing dt-method-*-deep.instructions.md files for structural precedent.

Output: research summary from Phase 1 above

Phase 2: Plan

Steps:

1. Review the research output from Phase 1.
2. Plan the deep instruction file structure — fidelity translation section, technology selection framework, specification patterns, manufacturing-specific hi-fi patterns.
3. Define section ordering, token allocation, and confirm empty applyTo.

Starter prompt:

/task-plan

Plan for dt-method-07-deep.instructions.md (on-demand deep file)

Using the Phase 1 research output, plan the deep instruction file:

- Fidelity translation section with mapping matrix and anti-patterns
- Technology selection framework for choosing tools per fidelity level
- Specification patterns — structured templates for converting prototypes to specs
- Manufacturing-specific hi-fi patterns from DT4HVE domain content
- On-demand loading structure — empty applyTo, loaded via read_file by the coach
- Content must support all 3 hats — organize sections clearly by hat affinity
- Content must clearly go beyond what the method-tier file already covers
- Section ordering and token budget allocation (~2,000-3,000 tokens)

Output: plan at .copilot-tracking/plans/{date}-dt-method-07-deep-plan.md

Phase 3: Build

Steps:

1. Review the plan from Phase 2.
2. Author the instruction file using /prompt-build.
3. Content must support all 3 hats — organize sections clearly by hat affinity so the coach can locate relevant advanced material quickly.

Starter prompt:

/prompt-build file=.github/instructions/dt-method-07-deep.instructions.md

Build using the plan at .copilot-tracking/plans/{date}-dt-method-07-deep-plan.md.

This is an on-demand deep instruction file for Method 7: Hi-Fi Prototypes. Key authoring notes:
- applyTo is EMPTY — this file is loaded on-demand by the coach, not auto-loaded by glob
- Content provides advanced/deep-dive material beyond the basic method-tier file
- Content must support all 3 hats — organize sections clearly by hat affinity
- Advanced fidelity translation with mapping matrix and anti-patterns
- Technology selection framework for choosing the right tools per fidelity level
- Specification writing frameworks for converting prototypes to implementable specs
- Manufacturing-specific hi-fi patterns from DT4HVE domain expertise
- Writing style: guidance over commands — deep reference material, not procedural steps
- Token budget: ~2,000-3,000 tokens

Phase 4: Review

Steps:

1. Review the built file against prompt-builder standards and the issue requirements.
2. Validate 3-hat coverage, fidelity translation depth, specification quality, and prompt-builder compliance.

Starter prompt:

/task-review

Review: .github/instructions/dt-method-07-deep.instructions.md

Validate against:
- prompt-builder.instructions.md authoring standards
- 3-hat coverage — advanced material organized by hat affinity (Fidelity Translator, Technical Architect, Specification Writer)
- Fidelity translation depth — advanced mapping with anti-patterns, not just basic fidelity levels
- Specification quality — structured frameworks for converting prototypes to specs
- Empty applyTo in frontmatter (on-demand loading)
- Writing style: guidance over commands
- Token budget: ~2,000-3,000 tokens
- Structural consistency with other deep-tier instruction files

After Review

• Pass: Mark complete.
• Iterate: Address review findings, rebuild, re-review.
• Escalate: If blocked by missing DT4HVE source material or architectural questions, raise to the user.

Authoring Standards

Follow .github/instructions/prompt-builder.instructions.md:

• Empty applyTo: since this is on-demand content
• Writing style: guidance over commands
• Organized by hat affinity to help the coach locate relevant content quickly

Success Criteria

• File created at .github/instructions/dt-method-07-deep.instructions.md
• Frontmatter has empty applyTo: (on-demand loading)
• Advanced fidelity translation with mapping matrix and anti-patterns
• Technology selection framework with prototype-appropriate decision guidance
• Specification writing patterns with audience mapping and assumption documentation
• Manufacturing-specific hi-fi patterns including PLC/SCADA and digital twin prototyping
• Content organized to support all 3 specialized hats
• Token count within ~2,000-3,000 target
• Passes task-reviewer validation against prompt-builder standards
• Each prompt, instructions, or agent file registered in collections/design-thinking.collection.yml with path and kind fields
• Each prompt, instructions, or agent file registered in collections/hve-core-all.collection.yml with path and kind fields
• npm run plugin:generate succeeds after collection manifest updates